The need for fairness in machine learning algorithms is increasingly critical. A recent focus has been on developing fair versions of classical algorithms, such as those for bandit learning, regression, and clustering. We extend this line of work to include algorithms for optimization subject to one or multiple matroid constraints. We map out this problem space, showing optimal solutions, approximation algorithms, or hardness results depending on the specific problem flavor. Our algorithms are efficient and empirical experiments demonstrate that fairness is achievable without a large compromise to the overall objective
The use of machine learning models in consequential decision making often exacerbates societal inequ...
Machine learning based systems are reaching society at large and in many aspects of everyday life. T...
In past work on fairness in machine learning, the focus has been on forcing the prediction of classi...
The need for fairness in machine learning algorithms is increasingly critical. A recent focus has be...
This article deals with the fair allocation of indivisible goods and its generalization to matroids....
A matroid is a notion of independence in combi-natorial optimization that characterizes problems tha...
We analyze the performance of evolutionary algorithms on various matroid optimization problems that ...
A matroid is a notion of independence in combi-natorial optimization which is closely related to com...
As machine learning algorithms grow in popularity and diversify to many industries, ethical and lega...
The goal of fairness in classification is to learn a classifier that does not discriminate against g...
We consider the problem of allocating a set of indivisible goods among a group of homogeneous agents...
This thesis investigates the problem of fair statistical learning. We argue that critical notions of...
International audienceUnwanted bias is a major concern in machine learning, raising in particular si...
We study the problem of optimizing nonlinear objective functions over matroids presented by oracles ...
A polymatroid is a polytope which is closely related to computational efficiency in polyhedral optim...
The use of machine learning models in consequential decision making often exacerbates societal inequ...
Machine learning based systems are reaching society at large and in many aspects of everyday life. T...
In past work on fairness in machine learning, the focus has been on forcing the prediction of classi...
The need for fairness in machine learning algorithms is increasingly critical. A recent focus has be...
This article deals with the fair allocation of indivisible goods and its generalization to matroids....
A matroid is a notion of independence in combi-natorial optimization that characterizes problems tha...
We analyze the performance of evolutionary algorithms on various matroid optimization problems that ...
A matroid is a notion of independence in combi-natorial optimization which is closely related to com...
As machine learning algorithms grow in popularity and diversify to many industries, ethical and lega...
The goal of fairness in classification is to learn a classifier that does not discriminate against g...
We consider the problem of allocating a set of indivisible goods among a group of homogeneous agents...
This thesis investigates the problem of fair statistical learning. We argue that critical notions of...
International audienceUnwanted bias is a major concern in machine learning, raising in particular si...
We study the problem of optimizing nonlinear objective functions over matroids presented by oracles ...
A polymatroid is a polytope which is closely related to computational efficiency in polyhedral optim...
The use of machine learning models in consequential decision making often exacerbates societal inequ...
Machine learning based systems are reaching society at large and in many aspects of everyday life. T...
In past work on fairness in machine learning, the focus has been on forcing the prediction of classi...